# Zoom-to-Inpaint: Image Inpainting with High-Frequency Details

arXiv: https://arxiv.org/abs/2012.09401 · HTML: https://mlsanity.com/paper/2012.09401/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [Palette: Image-to-Image Diffusion Models](https://mlsanity.com/paper/2111.05826/) (2021)
- [Sketch-Guided Text-to-Image Diffusion Models](https://mlsanity.com/paper/2211.13752/) (2022)
- [Deep Learning-based Image and Video Inpainting: A Survey](https://mlsanity.com/paper/2401.03395/) (2024)
- [Differential Diffusion: Giving Each Pixel Its Strength](https://mlsanity.com/paper/2306.00950/) (2023)
- [Catch Missing Details: Image Reconstruction with Frequency Augmented Variational Autoencoder](https://mlsanity.com/paper/2305.02541/) (2023)
- [Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach](https://mlsanity.com/paper/2310.12004/) (2023)
- [FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation](https://mlsanity.com/paper/2311.12090/) (2023)
- [Semi-Supervised Video Inpainting with Cycle Consistency Constraints](https://mlsanity.com/paper/2208.06807/) (2022)
- [GeoComplete: Geometry-Aware Diffusion for Reference-Driven Image Completion](https://mlsanity.com/paper/2510.03110/) (2025)
- [Structure First Detail Next: Image Inpainting with Pyramid Generator](https://mlsanity.com/paper/2106.08905/) (2021)
- [Both Spatial and Frequency Cues Contribute to High-Fidelity Image Inpainting](https://mlsanity.com/paper/2307.07678/) (2023)
- [Time-variant Image Inpainting via Interactive Distribution Transition Estimation](https://mlsanity.com/paper/2506.23461/) (2025)

## Abstract (arXiv)

Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details. In this paper, we propose applying super-resolution to coarsely reconstructed outputs, refining them at high resolution, and then downscaling the output to the original resolution. By introducing high-resolution images to the refinement network, our framework is able to reconstruct finer details that are usually smoothed out due to spectral bias - the tendency of neural networks to reconstruct low frequencies better than high frequencies. To assist training the refinement network on large upscaled holes, we propose a progressive learning technique in which the size of the missing regions increases as training progresses. Our zoom-in, refine and zoom-out strategy, combined with high-resolution supervision and progressive learning, constitutes a framework-agnostic approach for enhancing high-frequency details that can be applied to any CNN-based inpainting method. We provide qualitative and quantitative evaluations along with an ablation analysis to show the effectiveness of our approach. This seemingly simple, yet powerful approach, outperforms state-of-the-art inpainting methods. Our code is available in https://github.com/google/zoom-to-inpaint